CrossFormer Embedding DeepLabv3+ for Remote Sensing Images Semantic Segmentation

High-resolution remote sensing image segmentation is a challenging task. In urban remote sensing, the presenceof occlusions and shadows often results in blurred or invisible object boundaries, thereby increasing the difficultyof segmentation. In this paper, an improved network with a cross-region self-attention mechanism for multi-scalefeatures based onDeepLabv3+is designed to address the difficulties of small object segmentation and blurred targetedge segmentation. First,we use CrossFormer as the backbone feature extraction network to achieve the interactionbetween large- and small-scale features, and establish self-attention associations between features at both large andsmall scales to capture global contextual feature information. Next, an improved atrous spatial pyramid poolingmodule is introduced to establish multi-scale feature maps with large- and small-scale feature associations, andattention vectors are added in the channel direction to enable adaptive adjustment of multi-scale channel features.The proposed networkmodel is validated using the PotsdamandVaihingen datasets. The experimental results showthat, compared with existing techniques, the network model designed in this paper can extract and fuse multiscaleinformation, more clearly extract edge information and small-scale information, and segment boundariesmore smoothly. Experimental results on public datasets demonstrate the superiority of ourmethod compared withseveral state-of-the-art networks.

Novel fuzzy uncertainty modeling for land cover classification based on clustering analysis

It is well known that there is a degree of fuzzy uncertainty in land cover classification using remote sensing (RS) images. In this article, we propose a novel fuzzy uncertainty modeling algorithm for representing the features of land cover patterns, and present an adaptive interval type-2 fuzzy clustering method. The proposed fuzzy uncertainty modeling method is performed in two main phases. First, the segmentation units of the input multi-spectral RS image data are subjected to objectbased interval-valued symbolic modeling. As a result, features for each land cover type are represented in the form of an intervalvalued symbolic vector, which describes the intra-class uncertainty better than the source data and improves the separability between different classes. Second, interval type-2 fuzzy sets are generated for each cluster based on the distance metric of the interval-valued vectors. This step characterizes the inter-class high-order fuzzy uncertainty and improves the classification accuracy. To demonstrate the advantages and effectiveness of the proposed approach, extensive experiments are conducted on two multispectral RS image datasets from regions with complex land cover characteristics, and the results are compared with those given by well-known fuzzy and conventional clustering algorithms.